~ / rigs / alphasafal / production-agent-skills

alphasafal/production-agent-skills

12 benchmarked Agent Skills for AI coding agents, by role — debugging, code review, incident response, CI/CD review, threat modeling, security audits, system design, data science, PRDs. Claude Code, Codex, Cursor, Copilot.

↗ GitHub ★ 1 MIT updated 27d ago collection Claude Code Claude plugin
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~185 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 0/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit alphasafal/production-agent-skills/skills ./rig-production-agent-skills/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit alphasafal/production-agent-skills/skills/data-scientist .claude/skills/data-scientist
$ npx degit alphasafal/production-agent-skills/skills/debugging-investigator .claude/skills/debugging-investigator
$ npx degit alphasafal/production-agent-skills/skills/deploy-pipeline-reviewer .claude/skills/deploy-pipeline-reviewer
$ npx degit alphasafal/production-agent-skills/skills/feature-to-production .claude/skills/feature-to-production
$ npx degit alphasafal/production-agent-skills/skills/frontend-ui-reviewer .claude/skills/frontend-ui-reviewer
$ npx degit alphasafal/production-agent-skills/skills/incident-responder .claude/skills/incident-responder
$ npx degit alphasafal/production-agent-skills/skills/product-manager .claude/skills/product-manager
$ npx degit alphasafal/production-agent-skills/skills/production-code-review .claude/skills/production-code-review
$ npx degit alphasafal/production-agent-skills/skills/repo-architect .claude/skills/repo-architect
$ npx degit alphasafal/production-agent-skills/skills/research-to-decision .claude/skills/research-to-decision
$ npx degit alphasafal/production-agent-skills/skills/security-auditor .claude/skills/security-auditor
$ npx degit alphasafal/production-agent-skills/skills/spec-and-plan .claude/skills/spec-and-plan
$ npx degit alphasafal/production-agent-skills/skills/system-design-reviewer .claude/skills/system-design-reviewer
$ npx degit alphasafal/production-agent-skills/skills/test-first-developer .claude/skills/test-first-developer
$ npx degit alphasafal/production-agent-skills/skills/threat-modeler .claude/skills/threat-modeler

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(git push --force:*)",
      "Read(**/*.pem)",
      "Read(.env)",
      "Read(~/.aws/**)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Bash(rm -rf *)",
      "Bash(sudo *)",
      "Bash(sudo:*)",
      "Bash(rm -rf /)",
      "Bash(git push -f:*)",
      "Read(.env.*)",
      "Bash(git reset --hard*)",
      "Bash(rm -rf /*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(gh pr merge *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(gh pr merge:*)",
      "Bash(gh pr create *)",
      "Bash(git reset --hard:*)",
      "Bash(npm publish:*)",
      "Bash(git rebase *)"
    ]
  }
}

Skills (15)

Similar rigs

copied ✓